CN105046868B - A kind of fire alarm method based on thermal infrared imager in long and narrow environment - Google Patents
A kind of fire alarm method based on thermal infrared imager in long and narrow environment Download PDFInfo
- Publication number
- CN105046868B CN105046868B CN201510332538.7A CN201510332538A CN105046868B CN 105046868 B CN105046868 B CN 105046868B CN 201510332538 A CN201510332538 A CN 201510332538A CN 105046868 B CN105046868 B CN 105046868B
- Authority
- CN
- China
- Prior art keywords
- image
- flame
- segmentation
- target
- fire alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims abstract description 22
- 238000003709 image segmentation Methods 0.000 claims abstract description 20
- 239000006185 dispersion Substances 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000001228 spectrum Methods 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 11
- 241000190070 Sarracenia purpurea Species 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 235000019504 cigarettes Nutrition 0.000 description 3
- 230000005855 radiation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The present invention is a kind of fire alarm method based on thermal infrared imager in long and narrow environment, this method pre-processes the infrared image in the collected long and narrow space of thermal infrared imager, then image segmentation is carried out in the way of connected domain, high temp objects are tentatively judged according to absolute temperature, doubtful high temp objects and cryogenic object, doubtful high temp objects region to the target image temperature after segmentation between 70-100 degree again, acquire continuous multiple frames video image, and further image segmentation and binaryzation are carried out to multi-frame video image, calculate the dispersion degree of target area after dividing, wedge angle number and height variation feature are as flame profile feature, according to flame profile feature, the decision algorithm for being taken based on probability statistics model carries out flame monitoring judgement to the flame in doubtful high-temperature targets region.Using the method for the present invention, fire source can more accurately being identified, distinguishing the influence of the jamming targets such as boiled water, early warning accuracy rate greatly improves.
Description
Technical field
The present invention relates to the fire alarm technologies in the long and narrow environment such as compartment, aircraft cabin, and in particular to Yi Zhong
Fire monitoring long and narrow, in the limited environment of illumination based on thermal infrared imager and method for early warning.
Background technique
The fire alarm of the long and narrow spaces such as motor train unit carriage or aircraft cabin generally uses cigarette sense to carry out fire alarm, due to
Be routed in motor train unit carriage or aircraft cabin it is more, it is sluggish in air circulation, there are fire monitoring delay and be easy affected by environment
The problems such as.Infrared thermal imaging technique is that the invisible infrared energy for issuing object is changed into visible thermal image, compared to can
Light-exposed camera, can according to the temperature of the infrared intensity judgment object of object, thus outside by a large amount of interference elimination,
Collected brightness region must distribute the stronger object of infra-red radiation.Using based on thermal infrared imager in motor train unit carriage
Flame monitoring, the fire behavior that can faster have found that it is likely that.But only so not enough, in fire alarm, due to some fire
Flame, the sense temperature such as lighter flame is not high, and the temperature of some interfering objects such as hot water is compared with these flame initial temperatures
It is higher, it is possible to cause to fail to report when actual flame judges or false-alarm.Therefore to carry out effective fire alarm must also
Effective flame monitoring algorithm is used on the basis of thermal infrared imager sensing temperature, exclusive PCR reduces false-alarm.For example, hot
The temperature of the jamming targets such as water is usually at 70-100 degrees Celsius, and the temperature of the flame of lighter is very fast due to radiating, perception
Hot-water radiant of the temperature probably with 70 degrees Celsius intensity it is similar, therefore infrared sensor can miss in this case
Sentence.That is: if setting 70 degrees Celsius for the temperature threshold for judging flame, hot water may be considered as flame and issue void
It is alert；It, may be the flame of early stage, such as the flame of lighter if setting 100 degrees Celsius for the temperature threshold for judging flame
It is possible to prison not measure, causes to fail to report.For above-mentioned problem, need to temperature 70-100 degrees Celsius of target carry out into
The judgement of one step, so that flame or the hot water etc. of distinguishing early stage interfere.
Method proposed by the present invention, using continuous multiple frames video information, is used on the basis of infrared temperature judges
Probabilistic model comprising flame dynamic shape etc., integrated temperature (i.e. radiation intensity) information, is monitored flame.Accurately know
Other fire source distinguishes the influence of the jamming targets such as boiled water, greatly improves early warning accuracy rate.
Summary of the invention
The object of the present invention is to overcome the problems of the prior art, for the special long and narrow environment of motor-car compartment/cabin,
The case where with being likely to occur, using continuous multiple frames video information, divides on the basis of thermal infrared imager carries out flame temperature monitoring
The shape feature for analysing flame, the fire alarm method of doubtful fire object is further monitored with shape feature.
To realize above-mentioned technical purpose and the technique effect, the invention is realized by the following technical scheme:
A kind of fire alarm method based on thermal infrared imager in long and narrow environment, method includes the following steps:
Infrared image in step 1) long and narrow space collected for thermal infrared imager pre-processes, image preprocessing
It is that image segmentation is tentatively carried out by the temperature difference between target and background, obtains the position of each target area；The side of image segmentation
Method includes the following steps:
Step 1.1) denoises original infrared picture data using median filtering method；
The image obtained after step 1.2) pretreatment includes ambient noise, target and fringe region, chooses quantization threshold pair
Pretreated image is transformed to the image of only 3 grey levels, this corresponding temperature value of 3 grey levels is respectively to be higher than
100 degree of high temperature, the low temperature lower than 70 degree, the doubtful high temperature between 70-100 degree；
Step 1.3) carries out image segmentation using connected domain mode to the image after greyscale transformation, is partitioned into multiple objects mesh
Mark；
Step 1.4) handles the connected region after image segmentation, removes the too small Low Temperature Target region of area and doubts
Like high-temperature targets region, the target after segmentation is divided into three classes by the remaining gray value according to target area: high temp objects, low temperature
Object, doubtful high temp objects；
Step 1.5) judges the target after segmentation, is respectively processed according to three kinds of situations below:
(1) if monitoring high temp objects, fire alarm signal is directly exported；
(2) if not monitoring high temp objects and doubtful high temp objects in the target of segmentation, fire alarm is not exported
Signal；
(3) if monitoring doubtful high temp objects in the target of segmentation, step 2 is gone to；
Doubtful high temp objects region of the step 2 to temperature in step 1) between 70-100 degree acquires continuous multiple frames video
Image, and further image segmentation and binaryzation are carried out to multi-frame video image, calculate the flame of target area after segmentation
Shape feature, the specific steps are that:
Step 2.1) re-starts image segmentation according to its gray value, counts the figure again to each frame image of acquisition
As the sum of the grayscale values standard variance in region, image binaryzation is carried out；
After step 2.2) image binaryzation, connected domain, the target object region after being divided are calculated；
Step 2.3) calculates three statistics in the target object region after segmentation: dispersion degree, wedge angle number and height change
Feature, and using dispersion degree, wedge angle number and height variation feature as flame profile feature；
Step 3) is taken based on probability statistics model according to the flame profile feature of the multi-frame video image in step 2
Decision algorithm carries out flame monitoring to the flame in doubtful high-temperature targets region, if it is decided that is flame, then issues fire alarm letter
Number；If it is determined that interfering object, then fire alarm signal is not triggered.
Further, image binaryzation is carried out to the region with the following method in the step 2.1), that is, uses formula:
(1)
Wherein,；,,
In formulaExist for image pixelGray value；Exist for image pixel after Threshold segmentationGray value；M, N is respectively the height and width of picture size, and unit is pixel；For image pixel gray level value
Mean value；For the standard deviation of image pixel gray level value；For binarization segmentation threshold value；For coefficient of standard deviation.
Further, the calculation method of dispersion degree, wedge angle number and height variation feature is as follows in the step 2.3):
Continuous N frame image is obtained, for the i-th frame image, it is assumed that the area of the target area in the image is, Zhou Changwei, then
Dispersion degreeIt is defined as follows:
(2)；
Wedge angle numberIt is defined as follows:
(3)
WhereinThe minimal face product value of flame can correctly be monitored for doubtful high-temperature area, i.e. target shared picture in the picture
Element and；
Height variation feature is defined as follows:
To extract doubtful flame region in image sequenceHigh degree of sequence set,Indicate high degree of sequence set
In haveA element, i.e.,Frame video, it is assumed that rightMake discrete cosine transform and obtains cosine coefficient set, then height change
Characteristic functionAre as follows:
(4)
WhereinFor the length of discrete cosine transform；For cosine transform coefficient；WhenWhen being worth bigger, explanation
A possibility that component is bigger in composing, and indicates flame is bigger.
Further, after calculating the dispersion degree, wedge angle number and height variation feature these three characteristic quantities, the base taken
It is as follows in the decision algorithm of probability statistics model:
(5)
Wherein,For the weight of character pair amount,, corresponding weight
It is bigger, illustrate more to focus on distinguishing flame with this feature when monitoring；For flame decision probability.
Further, flame threshold value of warning is set in the probability statistics model as 1, if the flame decision probabilityGreatly
In being equal to 1, fire alarm signal is provided；If the flame decision probabilityLess than 1, then fire alarm signal is not triggered.
The beneficial effects of the present invention are:
Monitoring method of the invention can quickly identify those fire sources for being easy to cause fire, while can also distinguish well
The influence of the interference such as boiled water, therefore in practical applications, the method for the present invention can achieve the fire alarm of prestissimo, and pre-
Alert accuracy rate is high, suitable for the long and narrow environment such as compartment, cabin.
Detailed description of the invention
Fig. 1 is the fire alarm overview flow chart based on thermal infrared imager in the present invention.
Specific embodiment
It is below with reference to the accompanying drawings and in conjunction with the embodiments, next that the present invention will be described in detail.
Shown in referring to Fig.1, a kind of fire alarm method based on thermal infrared imager in long and narrow environment, this method includes following
Step:
Infrared image in step 1) long and narrow space collected for thermal infrared imager pre-processes, image preprocessing
It is that image segmentation is tentatively carried out by the temperature difference between target and background, obtains the position of each target area；The side of image segmentation
Method includes the following steps:
Step 1.1) denoises original infrared picture data using median filtering method；
The image obtained after step 1.2) pretreatment includes ambient noise, target and fringe region, chooses quantization threshold pair
Pretreated image is transformed to the image of only 3 grey levels, this corresponding temperature value of 3 grey levels is respectively to be higher than
100 degree of high temperature, the low temperature lower than 70 degree, the doubtful high temperature between 70-100 degree；
Step 1.3) carries out image segmentation using connected domain mode to the image after greyscale transformation, is partitioned into multiple objects mesh
Mark；
Step 1.4) handles the connected region after image segmentation, removes the too small Low Temperature Target region of area and doubts
Like high-temperature targets region, the target after segmentation is divided into three classes by the remaining gray value according to target area: high temp objects, low temperature
Object, doubtful high temp objects；
Step 1.5) judges the target after segmentation, is respectively processed according to three kinds of situations below:
(1) if monitoring high temp objects, fire alarm signal is directly exported；
(2) if not monitoring high temp objects and doubtful high temp objects in the target of segmentation, fire alarm is not exported
Signal；
(3) if monitoring doubtful high temp objects in the target of segmentation, step 2 is gone to；
Doubtful high temp objects region of the step 2 to temperature in step 1) between 70-100 degree acquires continuous multiple frames video
Image, and further image segmentation and binaryzation are carried out to multi-frame video image, calculate the flame of target area after segmentation
Shape feature, the specific steps are that:
Step 2.1) re-starts image segmentation according to its gray value, counts the figure again to each frame image of acquisition
As the sum of the grayscale values standard variance in region, image binaryzation is carried out；
After step 2.2) image binaryzation, connected domain, the target object region after being divided are calculated；
Step 2.3) calculates three statistics in the target object region after segmentation: dispersion degree, wedge angle number and height change
Feature, and using dispersion degree, wedge angle number and height variation feature as flame profile feature；
Step 3) is taken based on probability statistics model according to the flame profile feature of the multi-frame video image in step 2
Decision algorithm carries out fire defector to the flame in doubtful high-temperature targets region, if it is decided that is flame, then issues fire alarm letter
Number；If it is determined that interfering object, then fire alarm signal is not triggered.
Image binaryzation is carried out to the region with the following method in the step 2.1), that is, uses formula:
(1)
Wherein,,,,
In formulaExist for image pixelGray value；Exist for image pixel after Threshold segmentationGray value；M, N is respectively the height and width of picture size, and unit is pixel；For image pixel gray level value
Mean value；For the standard deviation of image pixel gray level value；For binarization segmentation threshold value；For coefficient of standard deviation, sheet
It is taken in embodiment。
The calculation method of dispersion degree, wedge angle number and height variation feature is as follows in the step 2.3):
Continuous N frame image is obtained, for the i-th frame image, it is assumed that the area of the target area in the image is, Zhou Changwei, then
Dispersion degreeIt is defined as follows:
(2)；
Wedge angle numberIt is defined as follows:
(3)
WhereinThe minimal face product value of flame can correctly be monitored for doubtful high-temperature area, i.e. target shared picture in the picture
Element and, in the present embodiment=8；
Height variation feature is defined as follows:
To extract doubtful flame region in image sequenceHigh degree of sequence set,Indicate high degree of sequence set
In haveA element, i.e.,Frame video, it is assumed that rightMake discrete cosine transform and obtains cosine coefficient set, then height change
Characteristic functionAre as follows:
(4)
Wherein,For the length of discrete cosine transform；For cosine transform coefficient,, k=1,2,3 ...,- 1, h (n) is in n-th frame video image
The height of target flame, N refer to continuous N frame video image；WhenWhen being worth bigger, illustrate to compose interior component bigger, indicates
There is a possibility that flame bigger.In the present embodiment=N。
After calculating the dispersion degree, wedge angle number and height variation feature these three characteristic quantities, that takes is united based on probability
The decision algorithm for counting model is as follows:
(5)
Wherein,For the weight of character pair amount,, corresponding weight
It is bigger, illustrate more to focus on distinguishing flame with this feature when monitoring；For flame decision probability.
Flame threshold value of warning is set in the probability statistics model as 1, if the flame decision probabilityMore than or equal to 1, give
Fire alarm signal out；If the flame decision probabilityLess than 1, then fire alarm signal is not triggered.
In the present embodiment, it by taking motor train unit carriage as an example, is tested in motor train unit carriage monitoring environment, for compartment
Interior fire source that may be present simulates 4 type high temp objects, cigarette butt, the paper of burning, lighter flare and the stronger hot water of interference
Cup, experimental result are as follows:
1) lighted cigarette butt, though volume is small, it is open fire that it, which is still the object being burning, and temperature is very high, surface
200 DEG C~300 DEG C of temperature, 700 DEG C~800 DEG C of central temperature height, therefore can directly be supervised with the temperature value of thermal infrared imager
It measures and；
2) burning point of plain paper is at 130 DEG C or so, and the temperature for the paper being burning is much higher than this temperature, generally at 500 DEG C
More than, thus also can directly be detected with the temperature value of thermal infrared imager come；
3) lighter flare is because be gas burning, and quickly, sense temperature generally only has for aerial heat dissipation
70 DEG C~100 DEG C similar with the temperature of one glass of hot water, therefore, if only using thermal infrared imager, is judged using temperature, just
Hot water can be issued early warning as flare and cause to report by mistake because temperature threshold is low；Otherwise threshold value is high, will be lighter flare
It omits, causes to fail to report.
For above situation, in the present embodiment, by taking hot water cup and lighter flame as an example, their image is carried out fast
Then speed segmentation, the doubtful high-temperature area image after respectively being divided acquire continuous 10 frame hot water cup and lighter fire respectively
Flame infrared video sequence image, the statistical result of area, perimeter and height are as shown in the table:
Three statistics of hot water cup and lighter flame are calculated separately below:
(1) dispersion degree
It substitutes into dispersion degree calculation formula (2), the dispersion degree of hot water cup are as follows:；Point of lighter flame
Divergence are as follows:；
(2) wedge angle number
In the present embodiment, the value of threshold value th takes 8, therefore, substitutes into wedge angle number calculation formula (3), obtains hot water cup
Wedge angle number and lighter flame wedge angle number it is equal are as follows:；
(3) height variation feature
It substitutes into height variation feature to calculate in function (4), the height variation feature of hot water cup are as follows:；The height variation feature of lighter flame are as follows:；
In the present embodiment, the corresponding weight of three statistics is respectively as follows:
The fire alarm value of hot water cup are as follows:
；
The fire alarm value of lighter flame are as follows:
；
Therefore, fire alarm signal is not triggered when target is hot water cup in doubtful high-temperature area；When target is sparking
When machine flame, fire alarm signal is provided.
Different data is taken to repeat above-described embodiment process, in doubtful high-temperature area, when the area of target is greater than threshold value th=8
When (i.e. 8 pixel values), accuracy is monitored 95% or more.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of fire alarm method in long and narrow environment based on thermal infrared imager, which is characterized in that this method includes following step
It is rapid:
Infrared image in step 1) long and narrow space collected for thermal infrared imager pre-processes, and image preprocessing is logical
The temperature difference crossed between target and background tentatively carries out image segmentation, obtains the position of each target area；The method packet of image segmentation
Include following steps:
Step 1.1) denoises original infrared picture data using median filtering method；
The image obtained after step 1.2) pretreatment includes ambient noise, target and fringe region, chooses quantization threshold to pre- place
Image after reason is transformed to the image of only 3 grey levels, this corresponding temperature value of 3 grey levels is respectively to be higher than 100
The high temperature of degree, the low temperature lower than 70 degree, the doubtful high temperature between 70-100 degree；
Step 1.3) carries out image segmentation using connected domain mode to the image after greyscale transformation, is partitioned into multiple objects target；
Step 1.4) handles the connected region after image segmentation, removes the too small Low Temperature Target region of area and doubtful height
Warm target area, it is remaining to be divided into three classes according to the gray value of target area: high temp objects, cryogenic object, doubtful high temp objects；
Step 1.5) judges the target after segmentation, is respectively processed according to three kinds of situations below:
(1) if monitoring high temp objects, fire alarm signal is directly exported；
(2) if not monitoring high temp objects and doubtful high temp objects in the target of segmentation, fire alarm signal is not exported；
(3) if monitoring doubtful high temp objects in the target of segmentation, step 2 is gone to；
Doubtful high temp objects region of the step 2 to temperature in step 1) between 70-100 degree acquires continuous multiple frames video figure
Picture, and further image segmentation and binaryzation are carried out to multi-frame video image, calculate the flame-shaped of target area after segmentation
Shape feature, the specific steps are that:
Step 2.1) re-starts image segmentation according to its gray value, counts the image district again to each frame image of acquisition
The sum of the grayscale values standard variance in domain carries out image binaryzation；
After step 2.2) image binaryzation, connected domain, the target object region after being divided are calculated；
Step 2.3) calculates three statistics in the target object region after segmentation: dispersion degree, wedge angle number and height variation feature,
And using dispersion degree, wedge angle number and height variation feature as flame profile feature；
Step 3) is taken based on the judgement of probability statistics model according to the flame profile feature of the multi-frame video image in step 2
Algorithm carries out flame monitoring to the flame in doubtful high-temperature targets region, if it is decided that is flame, then issues fire alarm signal；Such as
Fruit is determined as interfering object, then does not trigger fire alarm signal.
2. the fire alarm method in long and narrow environment according to claim 1 based on thermal infrared imager, which is characterized in that institute
It states in step 2.1) and image binaryzation is carried out to the region with the following method, that is, use formula:
(1)
Wherein,,,,
In formulaExist for image pixelGray value；Exist for image pixel after Threshold segmentationGray value；M, N is respectively the height and width of picture size, and unit is pixel；For image pixel gray level value
Mean value；For the standard deviation of image pixel gray level value；For binarization segmentation threshold value；For coefficient of standard deviation.
3. the fire alarm method in long and narrow environment according to claim 1 based on thermal infrared imager, which is characterized in that institute
The calculation method for stating dispersion degree in step 2.3), wedge angle number and height variation feature is as follows:
Continuous N frame image is obtained, for the i-th frame image, it is assumed that the area of the target area in the image is, Zhou Changwei,
Then
Dispersion degreeIt is defined as follows:
(2)；
Wedge angle numberIt is defined as follows:
(3)
WhereinThe minimal face product value of flame can correctly be monitored for doubtful high-temperature area, i.e. target shared pixel in the picture
With；
Height variation feature is defined as follows:
To extract doubtful high-temperature targets region in image sequenceHigh degree of sequence set,Indicate high degree of sequence set
In haveA element, i.e.,Frame video image, it is assumed that rightMake discrete cosine transform and obtains cosine coefficient set, then highly
Variation characteristic functionAre as follows:
(4)
WhereinFor the length of discrete cosine transform；For cosine transform coefficient；WhenWhen being worth bigger, illustrate to divide in spectrum
A possibility that amount is bigger, indicates flame is bigger.
4. the fire alarm method in long and narrow environment according to claim 1 or 3 based on thermal infrared imager, feature exist
In, after calculating the dispersion degree, wedge angle number and height variation feature these three characteristic quantities, take based on probability statistics model
Decision algorithm it is as follows:
(5)
Wherein,For the weight of character pair amount,, corresponding weight is bigger,
Illustrate more to focus on distinguishing flame with this feature when monitoring；For flame decision probability.
5. the fire alarm method in long and narrow environment according to claim 4 based on thermal infrared imager, which is characterized in that institute
It states and sets flame threshold value of warning in probability statistics model as 1, if the flame decision probabilityMore than or equal to 1, it is pre- to provide fire
Alert signal；If the flame decision probabilityLess than 1, then fire alarm signal is not triggered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510332538.7A CN105046868B (en) | 2015-06-16 | 2015-06-16 | A kind of fire alarm method based on thermal infrared imager in long and narrow environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510332538.7A CN105046868B (en) | 2015-06-16 | 2015-06-16 | A kind of fire alarm method based on thermal infrared imager in long and narrow environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105046868A CN105046868A (en) | 2015-11-11 |
| CN105046868B true CN105046868B (en) | 2019-09-20 |
Family
ID=54453378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510332538.7A Active CN105046868B (en) | 2015-06-16 | 2015-06-16 | A kind of fire alarm method based on thermal infrared imager in long and narrow environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105046868B (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426840A (en) * | 2015-11-18 | 2016-03-23 | 成都中昊英孚科技有限公司 | Multi-feature fusion based infrared forest fire judgment method |
| CN107256566B (en) * | 2017-05-26 | 2019-10-29 | 北京环境特性研究所 | Forest fires detection method based on radiation energy |
| CN107246913B (en) * | 2017-06-05 | 2019-11-08 | 山东神戎电子股份有限公司 | Based on the multiple forest fire protection detection method for differentiating mechanism |
| CN107025753B (en) * | 2017-06-05 | 2020-02-04 | 天津汉光祥云信息科技有限公司 | Wide area fire alarm device based on multispectral image analysis |
| CN107330884B (en) * | 2017-07-06 | 2021-06-22 | 北京安宁威尔科技发展有限公司 | Ignition point detection method and device |
| CN108458790B (en) * | 2018-01-18 | 2020-04-14 | 上海瀚莅电子科技有限公司 | Fire scene danger degree and fire source point determining method and device and head-mounted equipment |
| CN108428326A (en) * | 2018-03-14 | 2018-08-21 | 海南师范大学 | A kind of eco-tour assessment management precaution information system |
| CN110501914B (en) * | 2018-05-18 | 2023-08-11 | 佛山市顺德区美的电热电器制造有限公司 | Security monitoring method, equipment and computer readable storage medium |
| CN110533872A (en) * | 2018-05-25 | 2019-12-03 | 中车株洲电力机车研究所有限公司 | A kind of fire alarm method for compartment |
| CN110536108B (en) * | 2018-05-26 | 2021-02-19 | 黄河水利职业技术学院 | On-site monitoring system based on desk main body |
| CN109101882A (en) * | 2018-07-09 | 2018-12-28 | 石化盈科信息技术有限责任公司 | A kind of image-recognizing method and system of fire source |
| CN109410222B (en) * | 2018-11-01 | 2023-02-03 | 浩云科技股份有限公司 | Flame detection method and device |
| CN109360370B (en) * | 2018-11-30 | 2021-06-29 | 广州高新兴机器人有限公司 | Robot-based smoke and fire detection method |
| CN109731258B (en) * | 2018-12-19 | 2021-03-26 | 沈阳天眼智云信息科技有限公司 | Transformer ignition point monitoring and fire extinguishing method and system based on infrared technology |
| CN111539239B (en) * | 2019-01-22 | 2023-09-22 | 杭州海康微影传感科技有限公司 | Open fire detection method, device and storage medium |
| CN109931791B (en) * | 2019-03-15 | 2019-12-27 | 山东建筑大学 | Leakage detection method for shell-and-tube heat exchanger |
| CN110263696A (en) * | 2019-06-17 | 2019-09-20 | 沈阳天眼智云信息科技有限公司 | Flame detection method based on infrared video |
| EP4000052A1 (en) | 2019-07-18 | 2022-05-25 | Carrier Corporation | Flame detection device and method |
| CN110555447A (en) * | 2019-09-06 | 2019-12-10 | 深圳市瑞讯云技术有限公司 | Fire detection method, fire detection device and storage medium |
| CN110717419A (en) * | 2019-09-25 | 2020-01-21 | 浙江万胜智能科技股份有限公司 | Method for extracting flame characteristics from video image |
| CN110827268A (en) * | 2019-11-11 | 2020-02-21 | 北京华科德科技有限公司 | Wide dynamic infrared image mapping display method |
| CN111739250B (en) * | 2020-07-01 | 2022-02-15 | 广东工业大学 | Fire detection method and system combining image processing technology and infrared sensor |
| CN113450373A (en) * | 2020-08-18 | 2021-09-28 | 中国人民解放军63729部队 | Optical live image-based real-time discrimination method for characteristic events in carrier rocket flight process |
| CN112598712A (en) * | 2020-12-28 | 2021-04-02 | 浙江天衡五维电子科技有限公司 | Solar blind ultraviolet plume detection method and warning system |
| CN112857580B (en) * | 2021-01-08 | 2023-03-07 | 湖南中冶长天节能环保技术有限公司 | High-temperature detection-discharge treatment method and system for activated carbon flue gas purification device |
| CN113256928A (en) * | 2021-05-14 | 2021-08-13 | 中科永安(六安)科技有限公司 | Fire detection method based on image recognition and temperature determination algorithm |
| CN113379628A (en) * | 2021-06-07 | 2021-09-10 | 中国民用航空飞行学院 | Method for detecting thermal runaway of lithium battery based on infrared thermal imager |
| CN113344909B (en) * | 2021-07-01 | 2023-12-08 | 中国石油大学(北京) | Method and device for identifying and displaying flame penetration height Wen Lvjing coking of thermal power boiler |
| CN113274681B (en) * | 2021-07-21 | 2021-11-05 | 北京京能能源技术研究有限责任公司 | Intelligent track robot system and control method thereof |
| CN113562363B (en) * | 2021-08-20 | 2022-07-08 | 北京云迹科技股份有限公司 | Method for cleaning garbage can |
| CN114152347B (en) * | 2021-09-30 | 2024-06-14 | 国网黑龙江省电力有限公司电力科学研究院 | Comprehensive detection method for fault location and fire risk research and judgment of substation power equipment |
| CN114566028B (en) * | 2022-02-21 | 2024-05-07 | 招商蛇口数字城市科技有限公司 | Electric vehicle charging risk monitoring method, device and storage medium |
| CN115841731B (en) * | 2023-02-16 | 2023-05-05 | 广东汇通信息科技股份有限公司 | Infrared monitoring park fire early warning method |
| CN116758079B (en) * | 2023-08-18 | 2023-12-05 | 杭州浩联智能科技有限公司 | Harm early warning method based on spark pixels |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101315667A (en) * | 2008-07-04 | 2008-12-03 | 南京航空航天大学 | Multi-characteristic synthetic recognition method for outdoor early fire disaster |
| CN102743830A (en) * | 2012-07-10 | 2012-10-24 | 西安交通大学 | Automatic electric switch cabinet fire extinguishing system and fire recognition method |
| CN103400111A (en) * | 2013-07-10 | 2013-11-20 | 重庆大学 | Method for detecting fire accident on expressway or in tunnel based on video detection technology |
| CN104036611A (en) * | 2014-06-24 | 2014-09-10 | 北京中恩时代科技有限责任公司 | Fire detecting alarm method and detecting alarm apparatus implementing same |
| CN104091354A (en) * | 2014-07-30 | 2014-10-08 | 北京华戎京盾科技有限公司 | Fire detection method based on video images and fire detection device thereof |
| CN104408706A (en) * | 2014-09-30 | 2015-03-11 | 天津艾思科尔科技有限公司 | A method for detecting and locating fire based on double-waveband image |
-
2015
- 2015-06-16 CN CN201510332538.7A patent/CN105046868B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101315667A (en) * | 2008-07-04 | 2008-12-03 | 南京航空航天大学 | Multi-characteristic synthetic recognition method for outdoor early fire disaster |
| CN102743830A (en) * | 2012-07-10 | 2012-10-24 | 西安交通大学 | Automatic electric switch cabinet fire extinguishing system and fire recognition method |
| CN103400111A (en) * | 2013-07-10 | 2013-11-20 | 重庆大学 | Method for detecting fire accident on expressway or in tunnel based on video detection technology |
| CN104036611A (en) * | 2014-06-24 | 2014-09-10 | 北京中恩时代科技有限责任公司 | Fire detecting alarm method and detecting alarm apparatus implementing same |
| CN104091354A (en) * | 2014-07-30 | 2014-10-08 | 北京华戎京盾科技有限公司 | Fire detection method based on video images and fire detection device thereof |
| CN104408706A (en) * | 2014-09-30 | 2015-03-11 | 天津艾思科尔科技有限公司 | A method for detecting and locating fire based on double-waveband image |
Non-Patent Citations (2)
| Title |
|---|
| 基于嵌入式系统和红外图像的火焰检测算法;徐之; 韩斌; 宋敬海; 何文媛;《科学技术与工程》;20080101;第8卷(第1期);全文 * |
| 隧道火灾红外双目视觉定位系统研究;高荣;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150315(第 03 期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105046868A (en) | 2015-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105046868B (en) | A kind of fire alarm method based on thermal infrared imager in long and narrow environment | |
| CN105512667B (en) | Infrared and visible light video image fusion recognition fire method | |
| EP3265782B1 (en) | Wavelength band based passive infrared gas imaging | |
| Qureshi et al. | QuickBlaze: early fire detection using a combined video processing approach | |
| CN103761826B (en) | The recognition methods of a kind of thermal imaging video two mirror forest fires recognition system | |
| WO2016138991A1 (en) | Quantifying gas in passive optical gas imaging | |
| CN104050478A (en) | Smog detection method and system | |
| Chacon-Murguia et al. | Thermal video analysis for fire detection using shape regularity and intensity saturation features | |
| KR101224494B1 (en) | Video based smoke detection method robust to light conditions | |
| WO2009136895A1 (en) | System and method for video detection of smoke and flame | |
| KR100862409B1 (en) | The fire detection method using video image | |
| WO2018012050A1 (en) | Image processing device and image processing method | |
| CN111623882A (en) | Infrared body temperature monitoring method based on gun-ball linkage system | |
| CN103903020A (en) | Method and device for fire disaster image identification based on Code Books | |
| JP2019028957A (en) | Fire disaster identification apparatus | |
| Dukuzumuremyi et al. | A novel algorithm for fire/smoke detection based on computer vision | |
| JP6461511B2 (en) | Monitoring device and program | |
| Lai et al. | Robust little flame detection on real-time video surveillance system | |
| Ho | Nighttime fire/smoke detection system based on a support vector machine | |
| JP5279236B2 (en) | Target imaging detector | |
| CN109074714B (en) | Detection apparatus, method and storage medium for detecting event | |
| Khan et al. | Real-time fire detection using enhanced color segmentation and novel foreground extraction | |
| Zhang et al. | A flame detection algorithm based on video multi-feature fusion | |
| Lee et al. | Fire detection using color and motion models | |
| US20200011789A1 (en) | Wavelength band based passive infrared gas imaging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215000 No. 350 Qingcheng Mountain Road, hi tech Zone, Jiangsu, Suzhou Co-patentee after: BEIJING INSTITUTE OF TECHNOLOGY Patentee after: SUZHOU HUAQI INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 215000 No. 350 Qingcheng Mountain Road, hi tech Zone, Jiangsu, Suzhou Co-patentee before: BEIJING INSTITUTE OF TECHNOLOGY Patentee before: SUZHOU HUAQI INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No. 350 Qingchengshan Road, Science and Technology City, Suzhou High-tech Zone, Jiangsu Province Patentee after: SUZHOU HUAQI INTELLIGENT TECHNOLOGY Co.,Ltd. Patentee after: BEIJING INSTITUTE OF TECHNOLOGY Address before: No. 350 Qingchengshan Road, Science and Technology City, Suzhou High-tech Zone, Jiangsu Province Patentee before: SUZHOU HUAQI INTELLIGENT TECHNOLOGY Co.,Ltd. Patentee before: BEIJING INSTITUTE OF TECHNOLOGY |
|
| CP01 | Change in the name or title of a patent holder |